Sunghoon Im

18

Papers

7

Total Citations

Papers (18)

CAVIS: Context-Aware Video Instance Segmentation

JDEC: JPEG Decoding via Enhanced Continuous Cosine Coefficients

LOMM: Latest Object Memory Management for Temporally Consistent Video Instance Segmentation

JPEG Processing Neural Operator for Backward-Compatible Coding

Intrinsic Image Decomposition for Robust Self-supervised Monocular Depth Estimation on Reflective Surfaces

Stereo Matching With Color and Monochrome Cameras in Low-Light Conditions

High-Quality Depth From Uncalibrated Small Motion Clip

Noise Robust Depth From Focus Using a Ring Difference Filter

Robust Depth Estimation From Auto Bracketed Images

DRANet: Disentangling Representation and Adaptation Networks for Unsupervised Cross-Domain Adaptation

ADAS: A Direct Adaptation Strategy for Multi-Target Domain Adaptive Semantic Segmentation

Dynamic Neural Network for Multi-Task Learning Searching Across Diverse Network Topologies

High Quality Structure From Small Motion for Rolling Shutter Cameras

VolumeFusion: Deep Depth Fusion for 3D Scene Reconstruction

Facial Depth and Normal Estimation Using Single Dual-Pixel Camera

Towards Lossless Implicit Neural Representation via Bit Plane Decomposition

Style-Editor: Text-driven Object-centric Style Editing

Depth-discriminative Metric Learning for Monocular 3D Object Detection